scvi.external.MRVI#
- class scvi.external.MRVI(adata=None, registry=None, **model_kwargs)[source]#
Multi-resolution Variational Inference (MrVI) [Boyeau et al., 2025].
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object that has been registered via
setup_anndata().- n_latent
Dimensionality of the latent space for
z.- n_latent_u
Dimensionality of the latent space for
u.- encoder_n_hidden
Number of nodes per hidden layer in the encoder.
- encoder_n_layers
Number of hidden layers in the encoder.
- z_u_prior
Whether to use a prior for
z_u.- z_u_prior_scale
Scale of the prior for the difference between
zandu.- u_prior_scale
Scale of the prior for
u.- u_prior_mixture
Whether to use a mixture model for the
uprior.- u_prior_mixture_k
Number of components in the mixture model for the
uprior.- learn_z_u_prior_scale
Whether to learn the scale of the
zandudifference prior during training.- laplace_scale
Scale parameter for the Laplace distribution in the decoder.
- scale_observations
Whether to scale loss by the number of observations per sample.
- px_kwargs
Keyword args for
DecoderZXAttention.- qz_kwargs
Keyword args for
EncoderUZ.- qu_kwargs
Keyword args for
EncoderXU.
- adata anndata.AnnData |
Notes
This implementation of MRVI is in PyTorch. This will become the default version in v1.4.3 for MRVI. The JAX version is deprecated starting v1.5.
See further usage examples in the following tutorial:
See the user guide for this model:
See also
Attributes table#
Data attached to model instance. |
|
Manager instance associated with self.adata. |
|
The current device that the module's params are on. |
|
What the get normalized functions name is |
|
Returns computed metrics during training. |
|
Whether the model has been trained. |
|
The type of minified data associated with this model, if applicable. |
|
Data attached to model instance. |
|
Returns the run id of the model. |
|
Returns the run name of the model. |
|
Summary string of the model. |
|
Observations that are in test set. |
|
Observations that are in train set. |
|
Observations that are in validation set. |
Methods table#
|
Compute local statistics from counterfactual sample representations. |
|
Converts a legacy saved model (<v0.15.0) to the updated save format. |
|
Returns the object in AnnData associated with the key in the data registry. |
|
Deregisters the |
|
Compute the differential abundance between samples. |
|
Compute cell-specific multivariate differential expression. |
|
Computes the aggregated posterior over the |
|
Retrieves the |
|
Get the batch representation for a given set of indices. |
|
Compute the evidence lower bound (ELBO) on the data. |
|
Generate gene-gene correlation matrix using scvi uncertainty and expression. |
|
Returns the object in AnnData associated with the key in the data registry. |
|
Computes importance weights for the given samples. |
|
Returns the latent library size for each cell. |
|
Compute the latent representation of the data. |
|
Estimates for the parameters of the likelihood \(p(x \mid z)\). |
|
Compute local sample distances. |
|
Compute the local sample representation of the cells in the |
|
Compute the marginal log-likehood of the data. |
|
Returns the normalized (decoded) gene expression. |
|
Compute admissibility scores for cell-sample pairs. |
|
Compute the reconstruction error on the data. |
|
Returns the string provided to setup of a specific setup_arg. |
|
Returns the state registry for the AnnDataField registered with this instance. |
|
Variable names of input data. |
|
Instantiate a model from the saved output. |
|
Online update of a reference model with scArches algorithm [Lotfollahi et al., 2021]. |
|
Return the full registry saved with the model. |
|
Minify the model's |
|
Generate predictive samples from the posterior predictive distribution. |
|
Prepare data for query integration. |
|
Prepare multimodal dataset for query integration. |
|
Registers an |
|
Save the state of the model. |
|
Set up a model from on-disk AnnData files via the annbatch streaming loader. |
|
Sets up the |
|
Move the model to the device. |
|
Train the model. |
|
Transfer fields from a model to an AnnData object. |
|
Initialize/update metadata in the case where additional covariates are added. |
|
Update setup method args. |
|
Print summary of the setup for the initial AnnData or a given AnnData object. |
|
Prints summary of the registry. |
|
Print args used to setup a saved model. |
Prints setup kwargs used to produce a given registry. |
Attributes#
- MRVI.adata#
Data attached to model instance.
- MRVI.adata_manager#
Manager instance associated with self.adata.
- MRVI.device#
The current device that the module’s params are on.
- MRVI.get_normalized_function_name#
What the get normalized functions name is
- MRVI.history#
Returns computed metrics during training.
- MRVI.is_trained#
Whether the model has been trained.
- MRVI.minified_data_type#
The type of minified data associated with this model, if applicable.
- MRVI.registry#
Data attached to model instance.
- MRVI.run_id#
Returns the run id of the model. Used in MLFlow
- MRVI.run_name#
Returns the run name of the model. Used in MLFlow
- MRVI.summary_string#
Summary string of the model.
- MRVI.test_indices#
Observations that are in test set.
- MRVI.train_indices#
Observations that are in train set.
- MRVI.validation_indices#
Observations that are in validation set.
Methods#
- MRVI.compute_local_statistics(reductions, adata=None, indices=None, batch_size=None, use_vmap='auto', norm='l2', mc_samples=10, dataloader=None)[source]#
Compute local statistics from counterfactual sample representations.
Local statistics are reductions over either the local counterfactual latent representations or the resulting local sample distance matrices. For a large number of cells and/or samples, this method can avoid scalability issues by grouping over cell-level covariates.
- Parameters:
- reductions
list[MRVIReduction] List of reductions to compute over local counterfactual sample representations.
- adata anndata.AnnData |
None(default:None) AnnData object to use.
- indices
ArrayLike|None(default:None) Indices of cells to use.
- batch_size
int|None(default:None) Batch size to use for computing the local statistics.
- use_vmap
Literal['auto',True,False] (default:'auto') Whether to use vmap to compute the local statistics. If “auto”, vmap will be used if the number of samples is less than 500.
- norm
str(default:'l2') Norm to use for computing the distances.
- mc_samples
int(default:10) Number of Monte Carlo samples to use for computing the local statistics. Only applies if using sampled representations.
- reductions
- Return type:
- classmethod MRVI.convert_legacy_save(dir_path, output_dir_path, overwrite=False, prefix=None, **save_kwargs)[source]#
Converts a legacy saved model (<v0.15.0) to the updated save format.
- Parameters:
- dir_path
str Path to the directory where the legacy model is saved.
- output_dir_path
str Path to save converted save files.
- overwrite
bool(default:False) Overwrite existing data or not. If
Falseand directory already exists atoutput_dir_path, an error will be raised.- prefix
str|None(default:None) Prefix of saved file names.
- **save_kwargs
Keyword arguments passed into
save().
- dir_path
- Return type:
- MRVI.data_registry(registry_key)[source]#
Returns the object in AnnData associated with the key in the data registry.
- MRVI.deregister_manager(adata=None)[source]#
Deregisters the
AnnDataManagerinstance associated withadata.If
adataisNone, deregisters allAnnDataManagerinstances in both the class and instance-specific manager stores, except for the one associated with this model instance.
- MRVI.differential_abundance(adata=None, sample_cov_keys=None, sample_subset=None, compute_log_enrichment=False, omit_original_sample=True, batch_size=128)[source]#
Compute the differential abundance between samples.
Computes the logarithm of the ratio of the probabilities of each sample conditioned on the estimated aggregate posterior distribution of each cell.
- Parameters:
- adata anndata.AnnData |
None(default:None) The data object to compute the differential abundance for. If not given, the data object stored in the model is used.
- sample_cov_keys
list[str] |None(default:None) Keys for covariates (batch, etc.) that should also be taken into account when computing the differential abundance. At the moment, only discrete covariates are supported.
- sample_subset
list[str] |None(default:None) Only computes differential abundance for these sample labels.
- compute_log_enrichment
bool(default:False) Whether to compute the log enrichment scores for each covariate value.
- omit_original_sample
bool(default:True) If true, each cell’s sample-of-origin is discarded to compute aggregate posteriors. Only relevant if sample_cov_keys is not None.
- batch_size
int(default:128) Minibatch size for computing the differential abundance.
- adata anndata.AnnData |
- Return type:
- Returns:
A dataset with data variables:
"log_probs": Array of shape(n_cells, n_samples)containing the log probabilitiesfor each cell across samples.
"{cov_key}_log_probs": For each key insample_cov_keys, an array of shape(n_cells, _cov_values)containing the log probabilities for each cell across covariate values.
- MRVI.differential_expression(adata=None, sample_cov_keys=None, sample_subset=None, batch_size=128, use_vmap='auto', normalize_design_matrix=True, add_batch_specific_offsets=False, mc_samples=50, store_lfc=False, store_lfc_metadata_subset=None, store_baseline=False, eps_lfc=0.0001, filter_inadmissible_samples=False, lambd=0.0, delta=0.3, **filter_samples_kwargs)[source]#
Compute cell-specific multivariate differential expression.
For every cell, we first compute all counterfactual cell-state shifts, defined as
e_d = z_d - u, wherez_dis the latent representation of the cell for sampledanduis the sample-unaware latent representation. Then, we fit a linear model in each cell of the form:e_d = X_d * beta_d + iid gaussian noise.- Parameters:
- sample_cov_keys
list[str] |None(default:None) List of sample covariates to consider for the multivariate analysis. These keys should be present in
adata.obs.- adata anndata.AnnData |
None(default:None) AnnData object to use for computing the local sample representation. If
None, the analysis is performed on all cells in the dataset.- sample_subset
list[str] |None(default:None) Optional list of samples to consider for the multivariate analysis. If
None, all samples are considered.- batch_size
int(default:128) Batch size to use for computing the local sample representation.
- use_vmap
Literal['auto',True,False] (default:'auto') Whether to use vmap for computing the local sample representation.
- normalize_design_matrix
bool(default:True) Whether to normalize the design matrix.
- add_batch_specific_offsets
bool(default:False) Whether to offset the design matrix by adding batch-specific offsets to the design matrix. Setting this option to True is recommended when considering multi-site datasets.
- mc_samples
int(default:50) How many MC samples should be taken for computing betas.
- store_lfc
bool(default:False) Whether to store the log-fold changes in the module. Storing log-fold changes is memory-intensive and may require specifying a smaller set of cells to analyze, e.g., by specifying
adata.- store_lfc_metadata_subset
list[str] |None(default:None) Specifies a subset of metadata for which log-fold changes are computed. These keys must be a subset of
sample_cov_keys. Only applies whenstore_lfc=True.- store_baseline
bool(default:False) Whether to store the expression in the module if logfoldchanges are computed.
- eps_lfc
float(default:0.0001) Epsilon to add to the log-fold changes to avoid detecting genes with low expression.
- filter_inadmissible_samples
bool(default:False) Whether to filter out-of-distribution samples prior to performing the analysis.
- lambd
float(default:0.0) Regularization parameter for the linear model.
- delta
float|None(default:0.3) LFC threshold used to compute posterior DE probabilities. If None does not compute them to save memory consumption.
- filter_samples_kwargs
Keyword arguments to pass to
get_outlier_cell_sample_pairs().
- sample_cov_keys
- Return type:
- Returns:
A dataset containing the results of the differential expression analysis:
"beta": Coefficients for each covariate across cells and latent dimensions."effect_size": Effect sizes for each covariate across cells."pvalue": P-values for each covariate across cells."padj": Adjusted P-values for each covariate across cells using theBenjamini-Hochberg procedure.
"lfc": Log fold changes for each covariate across cells and genes, ifstore_lfcis
True.
"lfc_std": Standard deviation of log fold changes, ifstore_lfcisTrueanddeltais notNone.
"pde": Posterior DE probabilities, ifstore_lfcisTrueanddeltais notNone.
"baseline_expression": Baseline expression levels for each covariate across cells andgenes, if
store_baselineisTrue.
"n_samples": Number of admissible samples for each cell, iffilter_inadmissible_samplesisTrue.
- MRVI.get_aggregated_posterior(adata=None, sample=None, indices=None, batch_size=256)[source]#
Computes the aggregated posterior over the
ulatent representations.For the specified samples, it computes the aggregated posterior over the
ulatent representations. Returns a NumPyro MixtureSameFamily distribution.- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object to use. Defaults to the AnnData object used to initialize the model.
- sample
str|int|None(default:None) Name or index of the sample to filter on. If
None, uses all cells.- indices
ArrayLike|None(default:None) Indices of cells to use.
- batch_size
int(default:256) Batch size to use for computing the latent representation.
- adata anndata.AnnData |
- Return type:
- Returns:
A mixture distribution of the aggregated posterior.
- MRVI.get_anndata_manager(adata, required=False)[source]#
Retrieves the
AnnDataManagerfor a given AnnData object.Requires
self.idhas been set. Checks for anAnnDataManagerspecific to this model instance.- Parameters:
- Return type:
- MRVI.get_batch_representation(adata=None, indices=None, batch_size=None)[source]#
Get the batch representation for a given set of indices.
- Return type:
- MRVI.get_elbo(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, data_loader_kwargs=None, **kwargs)[source]#
Compute the evidence lower bound (ELBO) on the data.
The ELBO is the reconstruction error plus the Kullback-Leibler (KL) divergences between the variational distributions and the priors. It is different from the marginal log-likelihood; specifically, it is a lower bound on the marginal log-likelihood plus a term that is constant with respect to the variational distribution. It still gives good insights on the modeling of the data and is fast to compute.
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnDataobject withvar_namesin the same order as the ones used to train the model. IfNoneanddataloaderis alsoNone, it defaults to the object used to initialize the model.- indices
Sequence[int] |None(default:None) Indices of observations in
adatato use. IfNone, defaults to all observations. Ignored ifdataloaderis notNone.- batch_size
int|None(default:None) Minibatch size for the forward pass. If
None, defaults toscvi.settings.batch_size. Ignored ifdataloaderis notNone.- dataloader
Iterator[dict[str, torch.Tensor |None]] |None(default:None) An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of
Tensorwith keys as expected by the model. IfNone, a dataloader is created fromadata.- return_mean
bool(default:True) Whether to return the mean of the ELBO or the ELBO for each observation.
- data_loader_kwargs
dict|None(default:None) Keyword args for data loader, in dict form.
- **kwargs
Additional keyword arguments to pass into the forward method of the module.
- adata anndata.AnnData |
- Return type:
- Returns:
Evidence lower bound (ELBO) of the data.
Notes
This is not the negative ELBO, so higher is better.
- MRVI.get_feature_correlation_matrix(adata=None, indices=None, n_samples=10, batch_size=64, rna_size_factor=1000, transform_batch=None, correlation_type='spearman', silent=True)[source]#
Generate gene-gene correlation matrix using scvi uncertainty and expression.
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object with equivalent structure to initial AnnData. If
None, defaults to the AnnData object used to initialize the model.- indices
list[int] |None(default:None) Indices of cells in adata to use. If
None, all cells are used.- n_samples
int(default:10) Number of posterior samples to use for estimation.
- batch_size
int(default:64) Minibatch size for data loading into model. Defaults to
scvi.settings.batch_size.- rna_size_factor
int(default:1000) size factor for RNA prior to sampling gamma distribution.
- transform_batch
list[int|float|str] |None(default:None) Batches to condition on. If transform_batch is:
None, then real observed batch is used.
int, then batch transform_batch is used.
list of int, then values are averaged over provided batches.
- correlation_type
Literal['spearman','pearson'] (default:'spearman') One of “pearson”, “spearman”.
- silent
bool(default:True) If True, disables the progress bar. Default: False.
- adata anndata.AnnData |
- Return type:
- Returns:
Gene-gene correlation matrix
- MRVI.get_from_registry(adata, registry_key)[source]#
Returns the object in AnnData associated with the key in the data registry.
AnnData object should be registered with the model prior to calling this function via the
self._validate_anndatamethod.
- MRVI.get_importance_weights(adata, indices, qz, px, zs, max_cells=1024, truncation=False, n_mc_samples=500, n_mc_samples_per_pass=250, **data_loader_kwargs)[source]#
Computes importance weights for the given samples.
This method computes importance weights for every latent code in
zsas a way to encourage latent codes providing high likelihoods across many cells in the considered subpopulation.- Parameters:
- adata anndata.AnnData |
None Data to use for computing importance weights.
- indices
list[int] |None Indices of cells in adata to use.
- distributions
Dictionary of distributions associated with
indices.- qz
Distribution Variational posterior distributions of the cells, aligned with
indices.- px
Distribution Count distributions of the cells, aligned with
indices.- zs
Tensor Samples associated with
indices.- max_cells
int(default:1024) Maximum number of cells used to estimated the importance weights
- truncation
bool(default:False) Whether importance weights should be truncated. If True, the importance weights are truncated as described in [Ionides, 2008]. In particular, the provided value is used to threshold importance weights as a way to reduce the variance of the estimator.
- n_mc_samples
int(default:500) Number of Monte Carlo samples to use for estimating the importance weights, by default 500
- n_mc_samples_per_pass
int(default:250) Number of Monte Carlo samples to use for each pass, by default 250
- **data_loader_kwargs
Keyword args for data loader.
- adata anndata.AnnData |
- Return type:
- Returns:
importance_weights Numpy array containing importance weights aligned with the provided
indices.
Notes
This method assumes a normal prior on the latent space.
- MRVI.get_latent_library_size(adata=None, indices=None, give_mean=True, batch_size=None, dataloader=None, **data_loader_kwargs)[source]#
Returns the latent library size for each cell.
This is denoted as \(\ell_n\) in the scVI paper.
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object with equivalent structure to initial AnnData. If
None, defaults to the AnnData object used to initialize the model.- indices
list[int] |None(default:None) Indices of cells in adata to use. If
None, all cells are used.- give_mean
bool(default:True) Return the mean or a sample from the posterior distribution.
- batch_size
int|None(default:None) Minibatch size for data loading into model. Defaults to
scvi.settings.batch_size.- dataloader
Iterator[dict[str, torch.Tensor |None]] |None(default:None) An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of
Tensorwith keys as expected by the model. IfNone, a dataloader is created fromadata.- **data_loader_kwargs
Keyword args for data loader.
- adata anndata.AnnData |
- Return type:
- MRVI.get_latent_representation(adata=None, indices=None, batch_size=None, use_mean=True, give_z=False, dataloader=None)[source]#
Compute the latent representation of the data.
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object to use. Defaults to the AnnData object used to initialize the model.
- indices
ArrayLike|None(default:None) Indices of cells to use.
- batch_size
int|None(default:None) Batch size to use for computing the latent representation.
- use_mean
bool(default:True) Whether to use the mean of the distribution as the latent representation.
- give_z
bool(default:False) Whether to return the z latent representation or the u latent representation.
- dataloader
Iterator[dict[str, torch.Tensor |None]] |None(default:None) An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of
Tensorwith keys as expected by the model. IfNone, a dataloader is created fromadata.
- adata anndata.AnnData |
- Return type:
- Returns:
The latent representation of the data.
- MRVI.get_likelihood_parameters(adata=None, indices=None, n_samples=1, give_mean=False, batch_size=None, dataloader=None, **data_loader_kwargs)[source]#
Estimates for the parameters of the likelihood \(p(x \mid z)\).
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object with equivalent structure to initial AnnData. If
None, defaults to the AnnData object used to initialize the model.- indices
list[int] |None(default:None) Indices of cells in adata to use. If
None, all cells are used.- n_samples
int|None(default:1) Number of posterior samples to use for estimation.
- give_mean
bool|None(default:False) Return expected value of parameters or a samples
- batch_size
int|None(default:None) Minibatch size for data loading into model. Defaults to
scvi.settings.batch_size.- dataloader
Iterator[dict[str, torch.Tensor |None]] |None(default:None) An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of
Tensorwith keys as expected by the model. IfNone, a dataloader is created fromadata.- **data_loader_kwargs
Keyword args for data loader.
- adata anndata.AnnData |
- Return type:
- MRVI.get_local_sample_distances(adata=None, dataloader=None, batch_size=256, use_mean=True, normalize_distances=False, use_vmap='auto', groupby=None, keep_cell=True, norm='l2', mc_samples=10)[source]#
Compute local sample distances.
Computes cell-specific distances between samples, of size
(n_sample, n_sample), stored as a Dataset, with variable name"cell", of size(n_cell, n_sample, n_sample). If in addition,groupbyis provided, distances are also aggregated by group. In this case, the group-specific distances via the group name key.- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object to use for computing the local sample representation.
- dataloader
Iterator[dict[str, torch.Tensor |None]] |None(default:None) Inference dataloader to materialize when the model was initialized without AnnData.
- batch_size
int(default:256) Batch size to use for computing the local sample representation.
- use_mean
bool(default:True) Whether to use the mean of the latent representation as the local sample representation.
- normalize_distances
bool(default:False) Whether to normalize the local sample distances. Normalizes by the standard deviation of the original intra-sample distances. Only works with
use_mean=False.- use_vmap
Literal['auto',True,False] (default:'auto') Whether to use vmap for computing the local sample representation. Disabling vmap can be useful if running out of memory on a GPU.
- groupby
list[str] |str|None(default:None) List of categorical keys or single key of the anndata that is used to group the cells.
- keep_cell
bool(default:True) Whether to keep the original cell sample-sample distance matrices.
- norm
str(default:'l2') Norm to use for computing the local sample distances.
- mc_samples
int(default:10) Number of Monte Carlo samples to use for computing the local sample distances. Only relevant if
use_mean=False.
- adata anndata.AnnData |
- Return type:
- MRVI.get_local_sample_representation(adata=None, indices=None, batch_size=256, use_mean=True, use_vmap='auto')[source]#
Compute the local sample representation of the cells in the
adataobject.For each cell, it returns a matrix of size
(n_sample, n_features).- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object to use for computing the local sample representation.
- batch_size
int(default:256) Batch size to use for computing the local sample representation.
- use_mean
bool(default:True) Whether to use the mean of the latent representation as the local sample representation.
- use_vmap
Literal['auto',True,False] (default:'auto') Whether to use vmap for computing the local sample representation. Disabling vmap can be useful if running out of memory on a GPU.
- adata anndata.AnnData |
- Return type:
- MRVI.get_marginal_ll(adata=None, indices=None, n_mc_samples=1000, batch_size=None, return_mean=True, dataloader=None, data_loader_kwargs=None, **kwargs)[source]#
Compute the marginal log-likehood of the data.
The computation here is a biased estimator of the marginal log-likelihood of the data.
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnDataobject withvar_namesin the same order as the ones used to train the model. IfNoneanddataloaderis alsoNone, it defaults to the object used to initialize the model.- indices
Sequence[int] |None(default:None) Indices of observations in
adatato use. IfNone, defaults to all observations. Ignored ifdataloaderis notNone.- n_mc_samples
int(default:1000) Number of Monte Carlo samples to use for the estimator. Passed into the module’s
marginal_llmethod.- batch_size
int|None(default:None) Minibatch size for the forward pass. If
None, defaults toscvi.settings.batch_size. Ignored ifdataloaderis notNone.- return_mean
bool(default:True) Whether to return the mean of the marginal log-likelihood or the marginal-log likelihood for each observation.
- dataloader
Iterator[dict[str, torch.Tensor |None]] (default:None) An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of
Tensorwith keys as expected by the model. IfNone, a dataloader is created fromadata.- data_loader_kwargs
dict|None(default:None) Keyword args for data loader, in dict form.
- **kwargs
Additional keyword arguments to pass into the module’s
marginal_llmethod.
- adata anndata.AnnData |
- Return type:
float| torch.Tensor- Returns:
If
True, returns the mean marginal log-likelihood. Otherwise returns a tensor of shape(n_obs,)with the marginal log-likelihood for each observation.
Notes
This is not the negative log-likelihood, so higher is better.
- MRVI.get_normalized_expression(adata=None, indices=None, transform_batch=None, gene_list=None, library_size='latent', n_samples=1, n_samples_overall=None, weights=None, batch_size=None, return_mean=False, return_numpy=None, silent=True, dataloader=None, data_loader_kwargs=None, **importance_weighting_kwargs)[source]#
Returns the normalized (decoded) gene expression.
This is denoted as \(\rho_n\) in the scVI paper.
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object with equivalent structure to initial AnnData. If
None, defaults to the AnnData object used to initialize the model.- indices
list[int] |None(default:None) Indices of cells in adata to use. If
None, all cells are used.- transform_batch
list[int|float|str] |None(default:None) Batch to condition on. If transform_batch is: - None, then the real observed batch is used. - int, then batch transform_batch is used. - Otherwise based on string
- gene_list
list[str] |None(default:None) Return frequencies of expression for a subset of genes. This can save memory when working with large datasets, and few genes are of interest.
- library_size
float|Literal['latent'] (default:'latent') Scale the expression frequencies to a common library size. This allows gene expression levels to be interpreted on a common scale of relevant magnitude. If set to
"latent", use the latent library size.- n_samples
int(default:1) Number of posterior samples to use for estimation.
- n_samples_overall
int(default:None) Number of posterior samples to use for estimation. Overrides
n_samples.- weights
Literal['uniform','importance'] |None(default:None) Weights to use for sampling. If
None, defaults to"uniform".- batch_size
int|None(default:None) Minibatch size for data loading into the model. Defaults to
scvi.settings.batch_size.- return_mean
bool(default:False) Whether to return the mean of the samples.
- return_numpy
bool|None(default:None) Return a
ndarrayinstead of aDataFrame. DataFrame includes gene names as columns. If eithern_samples=1orreturn_mean=True, defaults toFalse. Otherwise, it defaults toTrue.- silent
bool(default:True) If True, disables the progress bar. Default: False.
- dataloader
Iterator[dict[str, torch.Tensor |None]] |None(default:None) An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of
Tensorwith keys as expected by the model. IfNone, a dataloader is created fromadata.- data_loader_kwargs
dict|None(default:None) Keyword args for data loader, in dict form.
- importance_weighting_kwargs
Keyword arguments passed into
get_importance_weights().
- adata anndata.AnnData |
- Return type:
- Returns:
If
n_samplesis provided andreturn_meanis False, this method returns a 3d tensor of shape (n_samples, n_cells, n_genes). Ifn_samplesis provided andreturn_meanis True, it returns a 2d tensor of shape (n_cells, n_genes). In this case, the return type isDataFrameunlessreturn_numpyis True. Otherwise, the method expectsn_samples_overallto be provided and returns a 2d tensor of shape (n_samples_overall, n_genes).
- MRVI.get_outlier_cell_sample_pairs(adata=None, subsample_size=5000, quantile_threshold=0.05, admissibility_threshold=0.0, batch_size=256)[source]#
Compute admissibility scores for cell-sample pairs.
This function computes the posterior distribution for u for each cell. Then, for every cell, it computes the log-probability of the cell under the posterior of each cell each sample and takes the maximum value for a given sample as a measure of admissibility for that sample. Additionally, it computes a threshold that determines if a cell-sample pair is admissible based on the within-sample admissibility scores.
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object containing the cells for which to compute the outlier cell-sample pairs.
- subsample_size
int(default:5000) Number of cells to use from each sample to approximate the posterior. If None, uses all of the available cells.
- quantile_threshold
float(default:0.05) Quantile of the within-sample log probabilities to use as a baseline for admissibility.
- admissibility_threshold
float(default:0.0) Threshold for admissibility. Cell-sample pairs with admissibility below this threshold are considered outliers.
- batch_size
int(default:256) Size of the batch to use for computing outlier cell-sample pairs.
- adata anndata.AnnData |
- Return type:
- MRVI.get_reconstruction_error(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, data_loader_kwargs=None, **kwargs)[source]#
Compute the reconstruction error on the data.
The reconstruction error is the negative log likelihood of the data given the latent variables. It is different from the marginal log-likelihood, but still gives good insights on the modeling of the data and is fast to compute. This is typically written as \(p(x \mid z)\), the likelihood term given one posterior sample.
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnDataobject withvar_namesin the same order as the ones used to train the model. IfNoneanddataloaderis alsoNone, it defaults to the object used to initialize the model.- indices
Sequence[int] |None(default:None) Indices of observations in
adatato use. IfNone, defaults to all observations. Ignored ifdataloaderis notNone- batch_size
int|None(default:None) Minibatch size for the forward pass. If
None, defaults toscvi.settings.batch_size. Ignored ifdataloaderis notNone- dataloader
Iterator[dict[str, torch.Tensor |None]] |None(default:None) An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of
Tensorwith keys as expected by the model. IfNone, a dataloader is created fromadata.- return_mean
bool(default:True) Whether to return the mean reconstruction loss or the reconstruction loss for each observation.
- data_loader_kwargs
dict|None(default:None) Keyword args for data loader, in dict form.
- **kwargs
Additional keyword arguments to pass into the forward method of the module.
- adata anndata.AnnData |
- Return type:
- Returns:
Reconstruction error for the data.
Notes
This is not the negative reconstruction error, so higher is better.
- MRVI.get_setup_arg(setup_arg)[source]#
Returns the string provided to setup of a specific setup_arg.
- Return type:
- MRVI.get_state_registry(registry_key)[source]#
Returns the state registry for the AnnDataField registered with this instance.
- Return type:
- classmethod MRVI.load(dir_path, adata=None, accelerator='auto', device='auto', prefix=None, backup_url=None, datamodule=None)[source]#
Instantiate a model from the saved output.
- Parameters:
- dir_path
str Path to saved outputs.
- adata
AnnData|MuData|None(default:None) AnnData organized in the same way as data used to train model. It is not necessary to run setup_anndata, as AnnData is validated against the saved
scvisetup dictionary. If None, will check for and load anndata saved with the model. If False, will load the model without AnnData.- accelerator
str(default:'auto') Supports passing different accelerator types
("cpu", "gpu", "tpu", "ipu", "hpu", "mps, "auto")as well as custom accelerator instances.- device
int|str(default:'auto') The device to use. Can be set to a non-negative index (
intorstr) or"auto"for automatic selection based on the chosen accelerator. If set to"auto"andacceleratoris not determined to be"cpu", thendevicewill be set to the first available device.- prefix
str|None(default:None) Prefix of saved file names.
- backup_url
str|None(default:None) URL to retrieve saved outputs from if not present on disk.
- datamodule
LightningDataModule|None(default:None) EXPERIMENTALALightningDataModuleinstance to use for training in place of the defaultDataSplitter. Can only be passed in if the model was not initialized withAnnData.
- dir_path
- Returns:
Model with loaded state dictionaries.
Examples
>>> model = ModelClass.load(save_path, adata) >>> model.get_....
- classmethod MRVI.load_query_data(adata=None, reference_model=None, registry=None, inplace_subset_query_vars=False, accelerator='auto', device='auto', unfrozen=False, freeze_dropout=False, freeze_expression=True, freeze_decoder_first_layer=True, freeze_batchnorm_encoder=True, freeze_batchnorm_decoder=False, freeze_classifier=True, transfer_batch=True, datamodule=None)[source]#
Online update of a reference model with scArches algorithm [Lotfollahi et al., 2021].
- Parameters:
- adata
AnnData|MuData(default:None) AnnData organized in the same way as data used to train model. It is not necessary to run setup_anndata, as AnnData is validated against the
registry.- reference_model
str|BaseModelClass(default:None) Either an already instantiated model of the same class or a path to saved outputs for the reference model.
- inplace_subset_query_vars
bool(default:False) Whether to subset and rearrange query vars inplace based on vars used to train the reference model.
- accelerator
str(default:'auto') Supports passing different accelerator types
("cpu", "gpu", "tpu", "ipu", "hpu", "mps, "auto")as well as custom accelerator instances.- device
int|str(default:'auto') The device to use. Can be set to a non-negative index (
intorstr) or"auto"for automatic selection based on the chosen accelerator. If set to"auto"andacceleratoris not determined to be"cpu", thendevicewill be set to the first available device.- unfrozen
bool(default:False) Override all other freeze options for a fully unfrozen model
- freeze_dropout
bool(default:False) Whether to freeze dropout during training
- freeze_expression
bool(default:True) Freeze neurons corresponding to expression in first layer
- freeze_decoder_first_layer
bool(default:True) Freeze neurons corresponding to first layer in decoder
- freeze_batchnorm_encoder
bool(default:True) Whether to freeze batchnorm weight and bias during training for encoder
- freeze_batchnorm_decoder
bool(default:False) Whether to freeze batchnorm weight and bias during training for decoder
- freeze_classifier
bool(default:True) Whether to freeze classifier completely. Only applies to
SCANVI.- transfer_batch
bool(default:True) Allow for surgery on the batch covariate. Only applies to
SYSVI.- datamodule
LightningDataModule|None(default:None) EXPERIMENTALALightningDataModuleinstance to use for training in place of the defaultDataSplitter. Can only be passed in if the model was not initialized withAnnData.
- adata
- static MRVI.load_registry(dir_path, prefix=None)[source]#
Return the full registry saved with the model.
- MRVI.minify_adata(minified_data_type='latent_posterior_parameters', use_latent_qzm_key='X_latent_qzm', use_latent_qzv_key='X_latent_qzv')[source]#
Minify the model’s
adata.Minifies the
AnnDataobject associated with the model according to the method specified byminified_data_typeand registers the new fields with the model’sAnnDataManager. This also sets theminified_data_typeattribute of the underlyingBaseModuleClassinstance.- Parameters:
- minified_data_type
Literal['latent_posterior_parameters'] (default:'latent_posterior_parameters') Method for minifying the data. One of the following:
"latent_posterior_parameters": Store the latent posterior mean and variance inobsmusing the keysuse_latent_qzm_keyanduse_latent_qzv_key.
- use_latent_qzm_key
str(default:'X_latent_qzm') Key to use for storing the latent posterior mean in
obsmwhenminified_data_typeis"latent_posterior".- use_latent_qzv_key
str(default:'X_latent_qzv') Key to use for storing the latent posterior variance in
obsmwhenminified_data_typeis"latent_posterior".
- minified_data_type
- Return type:
Notes
The modification is not done inplace – instead the model is assigned a new (minified) version of the
AnnData.
- MRVI.posterior_predictive_sample(adata=None, indices=None, transform_batch=None, n_samples=1, gene_list=None, batch_size=None, dataloader=None, silent=True, **data_loader_kwargs)[source]#
Generate predictive samples from the posterior predictive distribution.
The posterior predictive distribution is denoted as \(p(\hat{x} \mid x)\), where \(x\) is the input data and \(\hat{x}\) is the sampled data.
We sample from this distribution by first sampling
n_samplestimes from the posterior distribution \(q(z \mid x)\) for a given observation, and then sampling from the likelihood \(p(\hat{x} \mid z)\) for each of these.- Parameters:
- adata anndata.AnnData |
None(default:None) AnnDataobject with an equivalent structure to the model’s dataset. IfNone, defaults to theAnnDataobject used to initialize the model.- indices
list[int] |None(default:None) Indices of the observations in
adatato use. IfNone, defaults to all the observations.- transform_batch
list[int|float|str] |None(default:None) Batch to condition on. If transform_batch is: - None, then real observed batch is used. - int, then batch transform_batch is used. - Otherwise based on string
- n_samples
int(default:1) Number of Monte Carlo samples to draw from the posterior predictive distribution for each observation.
- gene_list
list[str] |None(default:None) Names of the genes to which to subset. If
None, defaults to all genes.- batch_size
int|None(default:None) Minibatch size to use for data loading and model inference. Defaults to
scvi.settings.batch_size. Passed intoBaseModelClass._make_data_loader.- dataloader
Iterator[dict[str, torch.Tensor |None]] |None(default:None) An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of
Tensorwith keys as expected by the model. IfNone, a dataloader is created fromadata.- **data_loader_kwargs
Keyword args for data loader.
- adata anndata.AnnData |
- Return type:
- Returns:
Sparse multidimensional array of shape
(n_obs, n_vars)ifn_samples == 1, else(n_obs, n_vars, n_samples).
- static MRVI.prepare_query_anndata(adata, reference_model, return_reference_var_names=False, inplace=True)[source]#
Prepare data for query integration.
This function will return a new AnnData object with padded zeros for missing features, as well as correctly sorted features.
- Parameters:
- adata
AnnData AnnData organized in the same way as data used to train model. It is not necessary to run setup_anndata, as AnnData is validated against the
registry.- reference_model
str|BaseModelClass Either an already instantiated model of the same class or a path to saved outputs for the reference model.
- return_reference_var_names
bool(default:False) Only load and return reference var names if True.
- inplace
bool(default:True) Whether to subset and rearrange query vars inplace or return new AnnData.
- adata
- Return type:
- Returns:
Query adata ready to use in
load_query_dataunlessreturn_reference_var_namesin which case a pd.Index of reference var names is returned.
- static MRVI.prepare_query_mudata(mdata, reference_model, return_reference_var_names=False, inplace=True)[source]#
Prepare multimodal dataset for query integration.
This function will return a new MuData object such that the AnnData objects for individual modalities are given padded zeros for missing features, as well as correctly sorted features.
- Parameters:
- mdata
MuData MuData organized in the same way as data used to train the model. It is not necessary to run setup_mudata, as MuData is validated against the
registry.- reference_model
str|BaseModelClass Either an already instantiated model of the same class or a path to saved outputs for the reference model.
- return_reference_var_names
bool(default:False) Only load and return reference var names if True.
- inplace
bool(default:True) Whether to subset and rearrange query vars inplace or return new MuData.
- mdata
- Return type:
- Returns:
Query mudata ready to use in
load_query_dataunlessreturn_reference_var_namesin which case a dictionary of pd.Index of reference var names is returned.
- classmethod MRVI.register_manager(adata_manager)[source]#
Registers an
AnnDataManagerinstance with this model class.Stores the
AnnDataManagerreference in a class-specific manager store. Intended for use in thesetup_anndata()class method followed up by retrieval of theAnnDataManagervia the_get_most_recent_anndata_manager()method in the model init method.Notes
Subsequent calls to this method with an
AnnDataManagerinstance referring to the same underlying AnnData object will overwrite the reference to previousAnnDataManager.
- MRVI.save(dir_path, prefix=None, overwrite=False, save_anndata=False, save_kwargs=None, legacy_mudata_format=False, datamodule=None, **anndata_write_kwargs)[source]#
Save the state of the model.
Neither the trainer optimizer state nor the trainer history are saved. Model files are not expected to be reproducibly saved and loaded across versions until we reach version 1.0.
- Parameters:
- dir_path
str Path to a directory.
- prefix
str|None(default:None) Prefix to prepend to saved file names.
- overwrite
bool(default:False) Overwrite existing data or not. If
Falseand directory already exists atdir_path, an error will be raised.- save_anndata
bool(default:False) If True, also saves the anndata
- save_kwargs
dict|None(default:None) Keyword arguments passed into
save().- legacy_mudata_format
bool(default:False) If
True, saves the modelvar_namesin the legacy format if the model was trained with aMuDataobject. The legacy format is a flat array with variable names across all modalities concatenated, while the new format is a dictionary with keys corresponding to the modality names and values corresponding to the variable names for each modality.- datamodule
LightningDataModule|None(default:None) EXPERIMENTALALightningDataModuleinstance to use for training in place of the defaultDataSplitter. Can only be passed in if the model was not initialized withAnnData.- anndata_write_kwargs
Kwargs for
write()
- dir_path
- classmethod MRVI.setup_annbatch(collection_path=None, paths=None, batch_key=None, labels_key=None, sample_key=None, unlabeled_category='Unknown', layer=None, categorical_covariate_keys=None, continuous_covariate_keys=None, rebuild=True, batch_size=4096, chunk_size=256, preload_nchunks=32, preload_to_gpu=True, dataset_size='20GB', shuffle=False, var_subset=None, merge=None, adatas=None, use_class_sampler=False, class_sampler_key=None, class_weights=None)[source]#
Set up a model from on-disk AnnData files via the annbatch streaming loader.
Builds (or reuses) a zarr-backed
DatasetCollectionfrom the supplied h5ad file paths, then wraps it in aAnnbatchDataModuleready for training.- Parameters:
- collection_path
str|None(default:None) Directory where the zarr collection is written (or already exists). If
None(default), a path is auto-generated as"./{ModelName}_annbatch.zarr"in the current working directory.- paths
list[str] |None(default:None) Paths to h5ad files that make up the training dataset. If
None, an existing collection atcollection_pathis opened without rebuilding — useful when the zarr store was created by a previous call. Must be provided when the store does not exist yet.- batch_key
str|None(default:None) Column in
obsto use as the batch variable.- labels_key
str|None(default:None) Column in
obsto use as the cell-type / label variable.- sample_key
str|None(default:None) Column in
obsto use as the sample variable. Used by models like MrVI.- unlabeled_category
str(default:'Unknown') Value used to mark unlabeled cells in
labels_key. Required by semi-supervised models such as SCANVI. Defaults to"Unknown".- layer
str|None(default:None) Layer in the h5ad files to use as the count matrix.
Noneusesadata.X(falling back toadata.raw.Xwhen a raw slot exists).- categorical_covariate_keys
list[str] |None(default:None) Additional categorical covariate columns in
obs.- continuous_covariate_keys
list[str] |None(default:None) Additional continuous covariate columns in
obs.- rebuild
bool(default:True) If
True, always rebuild the zarr collection even if it already exists on disk. IfFalse(default), reuse an existing collection and skip the (potentially expensive)add_adatasstep.- batch_size
int(default:4096) Number of cells per batch yielded by the
Loader.- chunk_size
int(default:256) Number of cells loaded from disk contiguously per read.
- preload_nchunks
int(default:32) Number of chunks to preload and shuffle in memory.
- preload_to_gpu
bool(default:True) Whether the loader should move data to GPU before yielding.
- dataset_size
int|str(default:'20GB') Number of observations to load into memory for shuffling / pre-processing when building the collection, or annbatch’s human-readable size strings, e.g.
"20GB".- shuffle
bool(default:False) Whether to pre-shuffle cells when building the collection.
- var_subset
list[str] |None(default:None) Optional list of gene names to restrict the collection to (passed as
var_subsettoadd_adatas).- merge
Literal['same','unique','first','only'] |None(default:None) How annbatch should merge
varmetadata across inputs. Passed through toannbatch.DatasetCollection.add_adatas().
- collection_path
- Returns:
AnnbatchDataModuleA configured datamodule whoseregistrycan be passed directly to the model constructor, e.g.model = SCVI(registry=dm.registry).
Notes
After training, saving and reloading the model requires reconstructing the datamodule manually and passing it to
load()via thedatamoduleargument — the same pattern used by all custom datamodules.
- classmethod MRVI.setup_anndata(adata, layer=None, sample_key=None, batch_key=None, labels_key=None, **kwargs)[source]#
Sets up the
AnnDataobject for this model.A mapping will be created between data fields used by this model to their respective locations in adata. None of the data in adata are modified. Only adds fields to adata.
- Parameters:
- adata
AnnData AnnData object. Rows represent cells, columns represent features.
- layer
str|None(default:None) if not
None, uses this as the key inadata.layersfor raw count data.- sample_key
str|None(default:None) key in
adata.obsfor sample information. Categories will automatically be converted into integer categories and saved toadata.obs['_scvi_sample']. IfNone, assigns the same sample to all the data.- batch_key
str|None(default:None) key in
adata.obsfor batch information. Categories will automatically be converted into integer categories and saved toadata.obs['_scvi_batch']. IfNone, assigns the same batch to all the data.- labels_key
str|None(default:None) key in
adata.obsfor label information. Categories will automatically be converted into integer categories and saved toadata.obs['_scvi_labels']. IfNone, assigns the same label to all the data.- **kwargs
Additional keyword arguments passed into
register_fields().
- adata
- MRVI.to_device(device)[source]#
Move the model to the device.
- Parameters:
Examples
>>> adata = scvi.data.synthetic_iid() >>> model = scvi.model.SCVI(adata) >>> model.to_device("cpu") # moves model to CPU >>> model.to_device("cuda:0") # moves model to GPU 0 >>> model.to_device(0) # also moves model to GPU 0
- MRVI.train(max_epochs=None, accelerator='auto', devices='auto', train_size=None, validation_size=None, batch_size=128, early_stopping=False, plan_kwargs=None, datamodule=None, **trainer_kwargs)[source]#
Train the model.
- Parameters:
- max_epochs
int|None(default:None) Maximum number of epochs to train the model. The actual number of epochs may be less if early stopping is enabled. If
None, defaults to a heuristic based onget_max_epochs_heuristic().- accelerator
str|None(default:'auto') Supports passing different accelerator types
("cpu", "gpu", "tpu", "ipu", "hpu", "mps, "auto")as well as custom accelerator instances.- devices
int|list[int] |str(default:'auto') The devices to use. Can be set to a non-negative index (
intorstr), a sequence of device indices (listor comma-separatedstr), the value-1to indicate all available devices, or"auto"for automatic selection based on the chosenaccelerator. If set to"auto"andacceleratoris not determined to be"cpu", thendeviceswill be set to the first available device.- train_size
float|None(default:None) Size of the training set in the range
[0.0, 1.0].- validation_size
float|None(default:None) Size of the validation set. If
None, defaults to1 - train_size. Iftrain_size + validation_size < 1, the remaining cells belong to a test set.- batch_size
int(default:128) Minibatch size to use during training.
- early_stopping
bool(default:False) Perform early stopping. Additional arguments can be passed in through
**kwargs. SeeTrainerfor further options.- plan_kwargs
dict|None(default:None) Additional keyword arguments passed into
TrainingPlan.- datamodule default:
None EXPERIMENTALALightningDataModuleinstance to use for training in place of the defaultDataSplitter.- **trainer_kwargs
Additional keyword arguments passed into
Trainer.
- max_epochs
- MRVI.transfer_fields(adata, **kwargs)[source]#
Transfer fields from a model to an AnnData object.
- Return type:
- MRVI.update_sample_info(adata=None, dataloader=None)[source]#
Initialize/update metadata in the case where additional covariates are added.
- Parameters:
- adata anndata.AnnData |
None(default:None) AnnData object to update the sample info with. Typically, this corresponds to the working dataset, where additional sample-specific covariates have been added.
- dataloader
Iterator[dict[str, torch.Tensor |None]] |None(default:None) Inference dataloader to materialize when the model was initialized without AnnData.
- adata anndata.AnnData |
Examples
>>> import scanpy as sc >>> from scvi.external import MRVI >>> MRVI.setup_anndata(adata, sample_key="sample_id") >>> model = MRVI(adata) >>> model.train() >>> # Update sample info with new covariates >>> sample_mapper = {"sample_1": "healthy", "sample_2": "disease"} >>> adata.obs["disease_status"] = adata.obs["sample_id"].map(sample_mapper) >>> model.update_sample_info(adata)
- MRVI.update_setup_method_args(setup_method_args)[source]#
Update setup method args.
- Parameters:
- setup_method_args
dict This is a bit of a misnomer, this is a dict representing kwargs of the setup method that will be used to update the existing values in the registry of this instance.
- setup_method_args
- MRVI.view_anndata_setup(adata=None, hide_state_registries=False)[source]#
Print summary of the setup for the initial AnnData or a given AnnData object.